glusterd: Ping timer implmentation

This patch refactors the existing client ping timer implementation, and makes
use of the common code for implementing both client ping timer and the
glusterd ping timer.

A new gluster rpc program for ping is introduced. The ping timer is only
started for peers that have this new program. The deafult glusterd ping
timeout is 30 seconds. It is configurable by setting the option
'ping-timeout' in glusterd.vol .

Also, this patch introduces changes in the glusterd-handshake path. The client
programs for a peer are now set in the callback of dump_versions, for both
the older handshake and the newer op-version handshake. This is the only place
in the handshake process where we know what programs a peer supports.

Change-Id: I035815ac13449ca47080ecc3253c0a9afbe9016a
BUG: 1038261
Signed-off-by: Vijaikumar M <vmallika@redhat.com>
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/5202
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

1 files changed, 15 insertions, 0 deletions

diff --git a/rpc/rpc-lib/src/rpc-clnt.c b/rpc/rpc-lib/src/rpc-clnt.c
index 3106342e970..46ee0eebcd0 100644
--- a/rpc/rpc-lib/src/rpc-clnt.c
+++ b/rpc/rpc-lib/src/rpc-clnt.c
@@ -17,6 +17,7 @@
 #define RPC_CLNT_DEFAULT_REQUEST_COUNT 512
 
 #include "rpc-clnt.h"
+#include "rpc-clnt-ping.h"
 #include "byte-order.h"
 #include "xdr-rpcclnt.h"
 #include "rpc-transport.h"
@@ -552,6 +553,7 @@ rpc_clnt_connection_cleanup (rpc_clnt_connection_t *conn)
                         gf_timer_call_cancel (clnt->ctx, conn->ping_timer);
                         conn->ping_timer = NULL;
                         conn->ping_started = 0;
+                        rpc_clnt_unref (clnt);
                 }
         }
         pthread_mutex_unlock (&conn->lock);
@@ -1000,6 +1002,17 @@ rpc_clnt_connection_init (struct rpc_clnt *clnt, glusterfs_ctx_t *ctx,
         }
         conn->rpc_clnt = clnt;
 
+        ret = dict_get_int32 (options, "ping-timeout",
+                              &conn->ping_timeout);
+        if (ret >= 0) {
+                gf_log (name, GF_LOG_DEBUG,
+                        "setting ping-timeout to %d", conn->ping_timeout);
+        } else {
+                gf_log (name, GF_LOG_INFO,
+                        "defaulting ping-timeout to 30secs");
+                conn->ping_timeout = 30;
+        }
+
         trans = rpc_transport_load (ctx, options, name);
         if (!trans) {
                 gf_log (name, GF_LOG_WARNING, "loading of new rpc-transport"
@@ -1592,6 +1605,7 @@ rpc_clnt_submit (struct rpc_clnt *rpc, rpc_clnt_prog_t *prog,
                 goto out;
         }
 
+        rpc_clnt_start_ping (rpc);
         ret = 0;
 
 out:
@@ -1734,6 +1748,7 @@ rpc_clnt_disable (struct rpc_clnt *rpc)
                         gf_timer_call_cancel (rpc->ctx, conn->ping_timer);
                         conn->ping_timer = NULL;
                         conn->ping_started = 0;
+                        rpc_clnt_unref (rpc);
                 }
                 trans = conn->trans;
                 conn->trans = NULL;